mihirp1998 / AlignPropView on GitHub
AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion
312Nov 1, 2024Updated last year

Alternatives and similar repositories for AlignProp

Users that are interested in AlignProp are comparing it to the libraries listed below

Sorting:

Are these results useful?